Covid-19¶

1.繪製全球的感染與康復人數，以國家別區分

2.利用地理資訊圖繪製全球感染、康復人數

In [1]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import plotly.graph_objects as go
pd.set_option('display.max_rows', None)
from plotly.subplots import make_subplots
import seaborn as sns
import datetime

導入數據¶

In [2]:
df = pd.read_csv('C:/Users/abcd8/OneDrive/桌面/resume/project5/covid_19_data.csv',encoding='utf-8')
df.head()
Out[2]:
SNo ObservationDate Province/State Country/Region Last Update Confirmed Deaths Recovered
0 1 01/22/2020 Anhui Mainland China 1/22/2020 17:00 1.0 0.0 0.0
1 2 01/22/2020 Beijing Mainland China 1/22/2020 17:00 14.0 0.0 0.0
2 3 01/22/2020 Chongqing Mainland China 1/22/2020 17:00 6.0 0.0 0.0
3 4 01/22/2020 Fujian Mainland China 1/22/2020 17:00 1.0 0.0 0.0
4 5 01/22/2020 Gansu Mainland China 1/22/2020 17:00 0.0 0.0 0.0
In [3]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 156292 entries, 0 to 156291
Data columns (total 8 columns):
 #   Column           Non-Null Count   Dtype  
---  ------           --------------   -----  
 0   SNo              156292 non-null  int64  
 1   ObservationDate  156292 non-null  object 
 2   Province/State   111979 non-null  object 
 3   Country/Region   156292 non-null  object 
 4   Last Update      156292 non-null  object 
 5   Confirmed        156292 non-null  float64
 6   Deaths           156292 non-null  float64
 7   Recovered        156292 non-null  float64
dtypes: float64(3), int64(1), object(4)
memory usage: 9.5+ MB
In [4]:
df.describe()
Out[4]:
SNo Confirmed Deaths Recovered
count 156292.000000 1.562920e+05 156292.000000 1.562920e+05
mean 78146.500000 2.844340e+04 966.090273 1.793232e+04
std 45117.758473 8.809800e+04 3278.110680 9.813018e+04
min 1.000000 -3.028440e+05 -178.000000 -8.544050e+05
25% 39073.750000 3.900000e+02 5.000000 1.000000e+01
50% 78146.500000 3.410000e+03 67.000000 7.570000e+02
75% 117219.250000 1.597875e+04 486.000000 6.270000e+03
max 156292.000000 1.867721e+06 45974.000000 4.174884e+06

產出報表、處理缺失值¶

In [5]:
import pandas_profiling
profile = pandas_profiling.ProfileReport(df)
profile.to_file("output1.html")
profile.to_widgets()
profile.to_notebook_iframe()

C:\Users\abcd8\AppData\Local\Temp\ipykernel_8728\2769708720.py:1: DeprecationWarning: `import pandas_profiling` is going to be deprecated by April 1st. Please use `import ydata_profiling` instead.
  import pandas_profiling

Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]
C:\Users\abcd8\AppData\Roaming\Python\Python38\site-packages\pandas_profiling\model\pandas\discretize_pandas.py:52: FutureWarning: In a future version, `df.iloc[:, i] = newvals` will attempt to set the values inplace instead of always setting a new array. To retain the old behavior, use either `df[df.columns[i]] = newvals` or, if columns are non-unique, `df.isetitem(i, newvals)`
  discretized_df.loc[:, column] = self._discretize_column(

Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]
Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]
Export report to file:   0%|          | 0/1 [00:00<?, ?it/s]
Render widgets:   0%|          | 0/1 [00:00<?, ?it/s]
SNo Confirmed Deaths Recovered
SNo 1.000000 0.426213 0.363542 0.364149
Confirmed 0.426213 1.000000 0.936324 0.552633
Deaths 0.363542 0.936324 1.000000 0.485000
Recovered 0.364149 0.552633 0.485000 1.000000
SNo ObservationDate Province/State Country/Region Last Update Confirmed Deaths Recovered
0 1 01/22/2020 Anhui Mainland China 1/22/2020 17:00 1.0 0.0 0.0
1 2 01/22/2020 Beijing Mainland China 1/22/2020 17:00 14.0 0.0 0.0
2 3 01/22/2020 Chongqing Mainland China 1/22/2020 17:00 6.0 0.0 0.0
3 4 01/22/2020 Fujian Mainland China 1/22/2020 17:00 1.0 0.0 0.0
4 5 01/22/2020 Gansu Mainland China 1/22/2020 17:00 0.0 0.0 0.0
5 6 01/22/2020 Guangdong Mainland China 1/22/2020 17:00 26.0 0.0 0.0
6 7 01/22/2020 Guangxi Mainland China 1/22/2020 17:00 2.0 0.0 0.0
7 8 01/22/2020 Guizhou Mainland China 1/22/2020 17:00 1.0 0.0 0.0
8 9 01/22/2020 Hainan Mainland China 1/22/2020 17:00 4.0 0.0 0.0
9 10 01/22/2020 Hebei Mainland China 1/22/2020 17:00 1.0 0.0 0.0
SNo ObservationDate Province/State Country/Region Last Update Confirmed Deaths Recovered
156282 156283 11/15/2020 Yukon Canada 2020-11-16 05:25:57 24.0 1.0 22.0
156283 156284 11/15/2020 Yunnan Mainland China 2020-11-16 05:25:57 217.0 2.0 209.0
156284 156285 11/15/2020 Zabaykalsky Krai Russia 2020-11-16 05:25:57 15222.0 219.0 12262.0
156285 156286 11/15/2020 Zacatecas Mexico 2020-11-16 05:25:57 13501.0 1120.0 0.0
156286 156287 11/15/2020 Zakarpattia Oblast Ukraine 2020-11-16 05:25:57 19384.0 468.0 8382.0
156287 156288 11/15/2020 Zaporizhia Oblast Ukraine 2020-11-16 05:25:57 18484.0 164.0 3021.0
156288 156289 11/15/2020 Zeeland Netherlands 2020-11-16 05:25:57 5041.0 86.0 0.0
156289 156290 11/15/2020 Zhejiang Mainland China 2020-11-16 05:25:57 1291.0 1.0 1279.0
156290 156291 11/15/2020 Zhytomyr Oblast Ukraine 2020-11-16 05:25:57 22225.0 368.0 12266.0
156291 156292 11/15/2020 Zuid-Holland Netherlands 2020-11-16 05:25:57 129188.0 2031.0 0.0 
VBox(children=(Tab(children=(Tab(children=(GridBox(children=(VBox(children=(GridspecLayout(children=(HTML(valu…
In [6]:
print(df.isna().any())

SNo                False
ObservationDate    False
Province/State      True
Country/Region     False
Last Update        False
Confirmed          False
Deaths             False
Recovered          False
dtype: bool
In [7]:
df.isna().sum()
Out[7]:
SNo                    0
ObservationDate        0
Province/State     44313
Country/Region         0
Last Update            0
Confirmed              0
Deaths                 0
Recovered              0
dtype: int64
In [8]:
NAN = [(c, df[c].isna().mean()*100) for c in df]
NAN_df = pd.DataFrame(NAN, columns =['column_name', 'percentage'])
NAN_df
Out[8]:
column_name percentage
0 SNo 0.000000
1 ObservationDate 0.000000
2 Province/State 28.352699
3 Country/Region 0.000000
4 Last Update 0.000000
5 Confirmed 0.000000
6 Deaths 0.000000
7 Recovered 0.000000
In [9]:
df.columns
Out[9]:
Index(['SNo', 'ObservationDate', 'Province/State', 'Country/Region',
       'Last Update', 'Confirmed', 'Deaths', 'Recovered'],
      dtype='object')
In [10]:
df['Province/State'] = df['Province/State'].fillna('Unknown')
df.isna().any()
Out[10]:
SNo                False
ObservationDate    False
Province/State     False
Country/Region     False
Last Update        False
Confirmed          False
Deaths             False
Recovered          False
dtype: bool
In [11]:
df.info()
df[['Confirmed', 'Deaths', 'Recovered']] = df[['Confirmed', 'Deaths', 'Recovered']].astype(int)
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 156292 entries, 0 to 156291
Data columns (total 8 columns):
 #   Column           Non-Null Count   Dtype  
---  ------           --------------   -----  
 0   SNo              156292 non-null  int64  
 1   ObservationDate  156292 non-null  object 
 2   Province/State   156292 non-null  object 
 3   Country/Region   156292 non-null  object 
 4   Last Update      156292 non-null  object 
 5   Confirmed        156292 non-null  float64
 6   Deaths           156292 non-null  float64
 7   Recovered        156292 non-null  float64
dtypes: float64(3), int64(1), object(4)
memory usage: 9.5+ MB
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 156292 entries, 0 to 156291
Data columns (total 8 columns):
 #   Column           Non-Null Count   Dtype 
---  ------           --------------   ----- 
 0   SNo              156292 non-null  int64 
 1   ObservationDate  156292 non-null  object
 2   Province/State   156292 non-null  object
 3   Country/Region   156292 non-null  object
 4   Last Update      156292 non-null  object
 5   Confirmed        156292 non-null  int32 
 6   Deaths           156292 non-null  int32 
 7   Recovered        156292 non-null  int32 
dtypes: int32(3), int64(1), object(4)
memory usage: 7.8+ MB

修改名稱、計算當日已感染尚未康復、死亡的人數¶

In [12]:
df['Country/Region'] = df['Country/Region'].replace('Mainland China','China')
df['Country/Region'] = df['Country/Region'].replace('US','United States')
df['Country/Region'] = df['Country/Region'].replace('UK','United Kingdom')
df.head()
Out[12]:
SNo ObservationDate Province/State Country/Region Last Update Confirmed Deaths Recovered
0 1 01/22/2020 Anhui China 1/22/2020 17:00 1 0 0
1 2 01/22/2020 Beijing China 1/22/2020 17:00 14 0 0
2 3 01/22/2020 Chongqing China 1/22/2020 17:00 6 0 0
3 4 01/22/2020 Fujian China 1/22/2020 17:00 1 0 0
4 5 01/22/2020 Gansu China 1/22/2020 17:00 0 0 0
In [13]:
df['Active_case'] = df['Confirmed'] - df['Deaths'] - df['Recovered']
df.head(5)
Out[13]:
SNo ObservationDate Province/State Country/Region Last Update Confirmed Deaths Recovered Active_case
0 1 01/22/2020 Anhui China 1/22/2020 17:00 1 0 0 1
1 2 01/22/2020 Beijing China 1/22/2020 17:00 14 0 0 14
2 3 01/22/2020 Chongqing China 1/22/2020 17:00 6 0 0 6
3 4 01/22/2020 Fujian China 1/22/2020 17:00 1 0 0 1
4 5 01/22/2020 Gansu China 1/22/2020 17:00 0 0 0 0

設定最近的日期

In [14]:
new_df = df[df['ObservationDate'] == max(df['ObservationDate'])].reset_index(drop=True)
new_df.head(5)
Out[14]:
SNo ObservationDate Province/State Country/Region Last Update Confirmed Deaths Recovered Active_case
0 155535 11/15/2020 Unknown Afghanistan 2020-11-16 05:25:57 43240 1617 35092 6531
1 155536 11/15/2020 Unknown Albania 2020-11-16 05:25:57 27830 623 12889 14318
2 155537 11/15/2020 Unknown Algeria 2020-11-16 05:25:57 67679 2154 44633 20892
3 155538 11/15/2020 Unknown Andorra 2020-11-16 05:25:57 5872 76 4747 1049
4 155539 11/15/2020 Unknown Angola 2020-11-16 05:25:57 13451 322 6444 6685

計算當日全球總數

In [15]:
df_world = new_df.groupby('ObservationDate')[['Confirmed', 'Deaths', 'Recovered','Active_case']].sum().reset_index()
df_world.head()
Out[15]:
ObservationDate Confirmed Deaths Recovered Active_case
0 11/15/2020 54370186 1317139 34955148 18097899
In [16]:
import plotly.figure_factory as ff

fig =  ff.create_table(df_world)
fig.update_layout(title_text='Coronavirus in the word : ')
fig.update_layout({'margin':{'t':50}})

fig.show()

以不同國家計算¶

In [17]:
ans = new_df.groupby('Country/Region')[['Confirmed','Deaths','Recovered','Active_case']].sum().reset_index()
In [18]:
ans.sort_values('Confirmed',ascending=False).head(10)
Out[18]:
Country/Region Confirmed Deaths Recovered Active_case
182 United States 11036935 246214 4174884 6615837
79 India 8845127 130070 8249579 465478
23 Brazil 5863093 165798 5279452 417843
61 France 1915713 42601 139760 1733352
142 Russia 1910149 32885 1429565 447699
162 Spain 1458591 40769 150376 1267446
181 United Kingdom 1372884 52026 3121 1317737
6 Argentina 1310491 35436 1129102 145953
37 Colombia 1198746 34031 1104956 59759
85 Italy 1178529 45229 420810 712490

全球確診、死亡、康復長條圖(以確診人數排序)¶

In [19]:
import plotly.express as px

wide_df = ans.sort_values('Confirmed',ascending=False)

fig = px.bar(wide_df, x="Country/Region", y=["Confirmed", "Deaths", "Recovered","Active_case"], title="Covid-19", text_auto=True)
fig.show()

當日確診前10國家

In [20]:
import plotly.express as px

wide_df = ans.sort_values('Confirmed',ascending=False).head(10)

fig = px.bar(wide_df, x="Country/Region", y=["Confirmed"], title="Confirmed", text_auto=True)
fig.show()

當日康復前10國家

In [21]:
import plotly.express as px

wide_df = ans.sort_values('Recovered',ascending=False).head(10)

fig = px.bar(wide_df, x="Country/Region", y=["Recovered"], title="Recovered", text_auto=True)
fig.show()

全球當日確診人數分布

In [22]:
from pyecharts import options as opts
from pyecharts.charts import Map

c = (
    Map()
    .add("Confirmed", [list(z) for z in zip(list(ans['Country/Region']), list(ans['Confirmed']))], "world")
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Convid-19確診人數分布"),
        visualmap_opts=opts.VisualMapOpts(max_=10000000),
    )
    .render_notebook()
)
c
Out[22]:

全球當日康復人數分布

In [23]:
from pyecharts import options as opts
from pyecharts.charts import Map

d = (
    Map()
    .add("Confirmed", [list(z) for z in zip(list(ans['Country/Region']), list(ans['Recovered']))], "world")
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
    .set_global_opts(
        title_opts=opts.TitleOpts(title="Convid-19康復人數分布"),
        visualmap_opts=opts.VisualMapOpts(max_=10000000),
    )
    .render_notebook()
)
d
Out[23]: